Learn R Programming

fastrtext (version 0.3.4)

'fastText' Wrapper for Text Classification and Word Representation

Description

Learning text representations and text classifiers may rely on the same simple and efficient approach. 'fastText' is an open-source, free, lightweight library that allows users to perform both tasks. It transforms text into continuous vectors that can later be used on many language related task. It works on standard, generic hardware (no 'GPU' required). It also includes model size reduction feature. 'fastText' original source code is available at .

Copy Link

Version

Install

install.packages('fastrtext')

Monthly Downloads

50

Version

0.3.4

License

MIT + file LICENSE

Issues

Pull Requests

Stars

Forks

Maintainer

Michael Benesty

Last Published

October 27th, 2019

Functions in fastrtext (0.3.4)

get_word_ids

Retrieve word IDs
print_help

Print help
predict.Rcpp_fastrtext

Get predictions (for supervised model)
get_word_vectors

Get word embeddings
train_sentences

Sentence corpus - train part
load_model

Load an existing fastText trained model
get_tokenized_text

Tokenize text
get_sentence_representation

Get sentence embedding
get_parameters

Export hyper parameters
get_nn

Get nearest neighbour vectors
test_sentences

Sentence corpus - test part
stop_words_sentences

Stop words list
build_vectors

Build fasttext vectors
execute

Execute command on fastText model (including training)
get_hamming_loss

Hamming loss
Rcpp_fastrtext-class

Rcpp_fastrtext class
add_prefix

Add a prefix to each word
build_supervised

Build a supervised fasttext model
fastrtext

fastrtext: 'fastText' Wrapper for Text Classification and Word Representation
add_tags

Add tags to documents
get_dictionary

Get list of known words
get_labels

Get list of labels (supervised model)
get_word_distance

Distance between two words